{"id":"https://openalex.org/W2132876818","doi":"https://doi.org/10.1145/1390334.1390549","title":"Pagerank based clustering of hypertext document collections","display_name":"Pagerank based clustering of hypertext document collections","publication_year":2008,"publication_date":"2008-07-20","ids":{"openalex":"https://openalex.org/W2132876818","doi":"https://doi.org/10.1145/1390334.1390549","mag":"2132876818"},"language":"en","primary_location":{"id":"doi:10.1145/1390334.1390549","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053557735","display_name":"Konstantin Avrachenkov","orcid":"https://orcid.org/0000-0002-8124-8272"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Konstantin Avrachenkov","raw_affiliation_strings":["INRIA Sophia Antipolis, Sophia Antipolis, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Sophia Antipolis, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075583507","display_name":"Vladimir Dobrynin","orcid":"https://orcid.org/0000-0003-4587-3094"},"institutions":[{"id":"https://openalex.org/I172901346","display_name":"St Petersburg University","ror":"https://ror.org/023znxa73","country_code":"RU","type":"education","lineage":["https://openalex.org/I172901346"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Vladimir Dobrynin","raw_affiliation_strings":["St. Petersburg State University, St. Petersburg, Russian Fed","St. Petersburg State University, St. Petersburg, Russian Fed.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg State University, St. Petersburg, Russian Fed","institution_ids":["https://openalex.org/I172901346"]},{"raw_affiliation_string":"St. Petersburg State University, St. Petersburg, Russian Fed.#TAB#","institution_ids":["https://openalex.org/I172901346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002349590","display_name":"Danil Nemirovsky","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Danil Nemirovsky","raw_affiliation_strings":["INRIA, Sophia Antipolis, France","[INRIA-Sophia Antipolis, France]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"[INRIA-Sophia Antipolis, France]","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Son Kim Pham","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Son Kim Pham","raw_affiliation_strings":["UCSD, San Diego, CA, USA","ucsd, san diego, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSD, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"ucsd, san diego, CA, USA#TAB#","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088641329","display_name":"Elena Smirnova","orcid":"https://orcid.org/0000-0003-3763-9951"},"institutions":[{"id":"https://openalex.org/I172901346","display_name":"St Petersburg University","ror":"https://ror.org/023znxa73","country_code":"RU","type":"education","lineage":["https://openalex.org/I172901346"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Elena Smirnova","raw_affiliation_strings":["St. Petersburg State University, St. Petersburg, Russian Fed","St. Petersburg State University, St. Petersburg, Russian Fed.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg State University, St. Petersburg, Russian Fed","institution_ids":["https://openalex.org/I172901346"]},{"raw_affiliation_string":"St. Petersburg State University, St. Petersburg, Russian Fed.#TAB#","institution_ids":["https://openalex.org/I172901346"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2519,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.88312466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"873","last_page":"874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.867154598236084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8143813610076904},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.7188352346420288},{"id":"https://openalex.org/keywords/hypertext","display_name":"Hypertext","score":0.7011448740959167},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.6608938574790955},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5046275854110718},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4938703179359436},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.488944411277771},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4258316159248352},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40445438027381897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30195873975753784},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17147445678710938},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16852182149887085}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.867154598236084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143813610076904},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7188352346420288},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.7011448740959167},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.6608938574790955},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5046275854110718},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4938703179359436},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.488944411277771},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4258316159248352},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40445438027381897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30195873975753784},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17147445678710938},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16852182149887085}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1390334.1390549","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.7305","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.7305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-sop.inria.fr/mistral/personnel/K.Avrachenkov/pubs/PRC.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00565355v1","is_oa":false,"landing_page_url":"https://inria.hal.science/inria-00565355","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International ACM SIGIR Conference on Research & Development in Information Retrieval, Jul 2008, Singapore, Singapore. pp.873--874, ⟨10.1145/1390334.1390549⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1535667454","https://openalex.org/W1554359467","https://openalex.org/W1573318337","https://openalex.org/W1854214752","https://openalex.org/W2020423193","https://openalex.org/W2109682749","https://openalex.org/W2121564430","https://openalex.org/W2151936673","https://openalex.org/W2170344111","https://openalex.org/W3031952539","https://openalex.org/W6631845447","https://openalex.org/W6676613663"],"related_works":["https://openalex.org/W2559422900","https://openalex.org/W3144143113","https://openalex.org/W4306940721","https://openalex.org/W2160785859","https://openalex.org/W4301002638","https://openalex.org/W2892323093","https://openalex.org/W3022637481","https://openalex.org/W3088133960","https://openalex.org/W2374506950","https://openalex.org/W3120229345"],"abstract_inverted_index":{"Clustering":[0],"hypertext":[1,41],"document":[2,17],"collection":[3],"is":[4,69],"an":[5],"important":[6],"task":[7],"in":[8],"Information":[9],"Retrieval.":[10],"Most":[11],"clustering":[12,35,64,75],"methods":[13],"are":[14],"based":[15,34,63,78],"on":[16],"content":[18,62,77],"and":[19,52,76],"do":[20],"not":[21],"take":[22],"into":[23],"account":[24],"the":[25,40,57],"hyper-text":[26],"links.":[27],"Here":[28],"we":[29],"propose":[30],"a":[31,70],"novel":[32],"PageRank":[33],"(PRC)":[36],"algorithm":[37,45,59],"which":[38],"uses":[39],"structure.":[42],"The":[43,54],"PRC":[44,58,74],"produces":[46],"graph":[47],"partitioning":[48],"with":[49,60],"high":[50],"modularity":[51],"coverage.":[53],"comparison":[55],"of":[56],"two":[61],"algorithms":[65],"shows":[66],"that":[67],"there":[68],"good":[71],"match":[72],"between":[73],"clustering.":[79]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}